DeepSeek seems to be slipping lately.
Model performance has been lagging for a while now — as of this writing, even its latest model still falls short compared to Claude Sonnet 4 and GPT-5.
DeepSeek Seems to Be Falling Behind
Summary
A zhichai.net forum post comments that DeepSeek appears to be dropping the ball. According to the author, DeepSeek's model performance has been falling behind for some time, and its latest model still cannot match Claude Sonnet 4 or GPT-5. The short post reflects a sentiment among some Chinese tech community observers that DeepSeek, despite earlier momentum, has lost its competitive edge in the frontier LLM race against leading Western models from Anthropic and OpenAI. No benchmarks are cited; the post expresses a personal assessment of model quality rather than detailed test results.
This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/175932888